AI Briefing
Yogiyo news
The latest AI and developer news from Yogiyo, with short summaries.
Visit website →Yegiaedae Overseas Tour Achieves 81% QA Resolution Rate in 25 Weeks with Monorepo-Based Development
Built 37 screens in 25 weeks by reusing the flight team's foundation
Yeogi-eottae Hosts Company-Wide Autumn Sports Day
Strengthening One-Team culture through a retro-themed competition featuring 8 teams and futsal
PickYeogi-eottae Builds Agentic RAG Operations and Evaluation System Using Langfuse and FastMCP
Accuracy improved by 3–9%p through LLM-as-a-judge and MCP specification optimization, applied to three internal services.
PickImplementing LightRAG and Navigator to Enhance Internal Document Search Accuracy
Yeogi-eottae combined LightRAG, based on GraphRAG, with Navigator, which reflects document hierarchy, to improve internal document search accuracy to 84%.
Yeogi-eottae Reduces API Migration Risks by Building a Shadowing Verification Dashboard
Yeogi-eottae's Exhibition Development Team built a shadowing verification dashboard using Grafana and Prometheus, reducing verification resources during API migration through common libraryization.
Here Travel: Building an AI-Powered ERD Tool—Reducing Failed Calls from 61 to 3
To address AI non-determinism, we developed an MCP-based ERD tool where AI handles design and the tool handles rendering.
Exhibition Development Team Enhances Incident Response Efficiency with Grafana-Based Observability Board
Sharing a case study on improving internal observability and fostering contributions by leveraging existing infrastructure and AI agents.
Resolving 'Intent Debt' in AI-Era Development Teams: Collaboration Strategies Centered on Guides and Context Sharing
To address the surge in outputs and 'intent debt' caused by AI adoption, the article proposes elevating decision-making processes into guides and sharing context through team reviews.
PickYeogi-eottae Company Builds Internal Deployment Platform 'Vibedog' for Non-Developers
Yeogi-eottae Company has built an internal deployment platform called 'Vibedog' for non-developers, which is currently being used by 58 teams across the company.
PickYeogi-eottae Processes 280 Overseas Tour QA Tickets with AI Agent, Achieving 56% Same-Day Resolution Rate
Yeogi-eottae used an AI agent to process 280 QA tickets for its overseas tour service, increasing the same-day resolution rate to 56% compared to previous projects and shortening lead times.
Aviation Frontend Construction Log: Structuring with Folder Name Prefix Symbols Instead of FSD
The aviation frontend team shared how they manage file impact scope using folder name prefix symbol rules instead of adopting FSD.
Solving Airline Frontend State Management with React Query and URL State, Without Global State Libraries
A case study on managing state using React Query and URL state without adopting global state libraries when building an airline frontend.
Building Aviation Frontend Authentication: Integrating Token Ingestion Paths for Web and App WebViews and httpOnly Cookie Handling Strategy
We built an authentication architecture that unifies disparate token ingestion paths from web and app webviews into httpOnly cookies, resolving timing issues.
Building a Personal LLM Wiki: Ensuring AI Memory Reliability with Immutable Sources and MOC Structure
By applying the immutable source principle and MOC structure to a personal LLM wiki, AI context-linking errors were reduced and the reliability of work memory was improved.
[Part 2] Plotting a 100k-Point Scatter Plot with a Custom Grafana Panel — 3 Pitfalls Revealed After Building It
This article summarizes the rendering, query, and incremental lookup optimization process encountered while implementing a 100k-point scatter plot using a custom Grafana plugin.
Yeogi-eottae Builds APM Scatter Chart with OpenTelemetry and ClickHouse
Yeogi-eottae built an APM scatter chart by integrating OpenTelemetry and ClickHouse to visualize the distribution of individual requests.
Yeogi-eottae QA Shares Perspective Shifts in Transitioning from Exhibition to Reservation and Settlement Verification
The Yeogi-eottae QA team shared how their verification methods and perspectives changed when transitioning from exhibition QA to reservation and settlement QA.
Yeogi-eottae Automates Design Repetition with AI-Based Introduction Builder
The Yeogi-eottae design team developed a builder that automates the introduction creation process by combining AI with existing SOPs.
Yeogi-eottae boosts purchase conversion rate with home screen seller card improvements: Effect of reducing 'Recently Viewed Items'
Yeogi-eottae achieved an increase in purchase conversion rate through an A/B test involving approximately 1 million users by improving home screen seller cards based on the JTBD framework.
Yeogi-eottae Home Card Improvement Project: Redefining Module Roles and Restructuring Navigation Based on A/B Testing
Yeogi-eottae conducted a project to address low click-through rates on its home screen by redefining module roles rather than product card formats and validating new navigation experiences through A/B testing.